google-scrape-mcp

by Maybeyes111

Overview Schema Source Related Servers Discussions Admin

Python

Local

Google Patents Search

google_patents_search

Read-onlyIdempotent

Search Google Patents by query to retrieve patent title, number, inventors, dates, and PDF links as JSON.

Instructions

Scrape Google Patents XHR JSON: title, number, inventors, dates, PDF.

page: 1-based (1 = first page). NOTE: page number lives INSIDE the url= query string (page=N), not as an outer param.

Rate-limited by Google: avoid rapid repeats; when the result is blocked, wait or switch to an RSS-based tool.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "google_patents_search"
  }
}

Input Schema

Name	Required	Description	Default
`num`	No
`page`	No
`query`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.2Sep 27, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower; the description adds real value with the rate-limit/blocking disclosure and the wait-or-switch remediation. It does not note pagination termination or result caps, but the blocking behavior is the operationally important trait.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and return fields, then the page gotcha, then the rate-limit caveat. Short and generally well ordered, though the 'url= query string' wording is slightly confusing given no url parameter exists in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no prose. The gaps are the undocumented num parameter and the absence of any query-format guidance for a patent search endpoint, which is a meaningful omission for a scraper-style tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It does explain that page is 1-based and, crucially, that the page number lives inside the url= query string rather than as an outer param — a non-obvious trap. But num (result count) and the query syntax itself go entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Scrape Google Patents XHR JSON') and enumerates the returned fields (title, number, inventors, dates, PDF), which cleanly separates it from the scholar/news/shopping siblings. An agent can tell what this does and what it yields without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is only implied — it is for patent lookups, and the description redirects to an 'RSS-based tool' when results are blocked, which is a genuine alternative signal. However, no guidance is given on when to prefer this over other search siblings or on what query forms are valid.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.